Observing the tree top distribution of sloping fruit trees with multi-spectral imagery and conducting traversal path planning for plant protection drones

Abstract

In recent years the agricultural population in Taiwan has been aging and the labor force is insufficient The slope topography requires a large amount of labor to spray pesticides and the inclined terrain is also likely to cause accidents If planted with drones it can save labor and protect farmers Safety In this study various multi-spectral images are used for observation and recording The most approximate estimation method is used to classify various images of multi-spectral images and the features of specific objects in multi-spectral images are found at a glance of the image And use the most approximate estimation to estimate the distribution of each object in the entire multi-spectral image and highlight the distribution of the longan tree According to the distribution size and location of the longan tree based on the spray range of the commercially available plant protection drones several points are designed to ensure that the plant protection drone completely sprays the pesticides on the fruit trees as the hovering area of the drone during flight The coordinates of the points are routed by the ant colony system in the ant colony algorithm According to multiple tests the best path that can pass through all hovering areas is measured

Date of Award	2019
Original language	English
Supervisor	Yueh-Min Huang (Supervisor)